Lung cancer identification: a review on detection and classification
- PDF / 667,394 Bytes
- 10 Pages / 595.276 x 790.866 pts Page_size
- 6 Downloads / 240 Views
NON-THEMATIC REVIEW
Lung cancer identification: a review on detection and classification Shailesh Kumar Thakur 1 & Dhirendra Pratap Singh 1
&
Jaytrilok Choudhary 1
# Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Lung cancer is one of the most common diseases among humans and one of the major causes of growing mortality. Medical experts believe that diagnosing lung cancer in the early phase can reduce death with the illustration of lung nodule through computed tomography (CT) screening. Examining the vast amount of CT images can reduce the risk. However, the CT scan images incorporate a tremendous amount of information about nodules, and with an increasing number of images make their accurate assessment very challenging tasks for radiologists. Recently, various methods are evolved based on handcraft and learned approach to assist radiologists. In this paper, we reviewed different promising approaches developed in the computeraided diagnosis (CAD) system to detect and classify the nodule through the analysis of CT images to provide radiologists’ assistance and present the comprehensive analysis of different methods. Keywords Lung cancer . Nodule . Classification . Detection . Malignant . Benign
1 Introduction According to database generated by International Agency of Research on Cancer (IARC) Global Cancer Observatory in 2018, they quoted the incidence and mortality rates across 185 countries and 36 types of cancers, in which lung cancer ranked at the top for the deaths in men and third most causes for the deaths in women. Almost 9.6 million cancer deaths reported in 2018 in which approximately 1.8 million deaths, about 18.4% of the total deaths due to lung cancer [1]. The worrying rise in deaths due to lung cancer and excessively high prevalence in nature, various cancer control research, and early detection methods have been introduced to control the mortality. Typically, lung cancer cure depends upon detection of disease at the initial stage, and effective diagnosing methods result in decrease incidence rates for lung cancers. Currently, the
* Shailesh Kumar Thakur [email protected] Dhirendra Pratap Singh [email protected] Jaytrilok Choudhary [email protected] 1
Computer Science and Engineering, Maulana Azad National Institute of Technology, Bhopal, India
treatment of lung cancer can be done through seven techniques such as chest radiographies (CXRs), computed tomography(CT) scans, magnetic resonance imaging (MRI), positron emission tomography (PET), and cytology sputum and breath analysis [2]. All the available detection techniques of lung cancer have different detection levels and various markers as shown in Table 1. These methods have certain demerits as well, e.g., CXR, septum, and CT are prone to radiation, whereas MRI and PET have limitations in detection and staging lung cancer. Moreover, serum is an invasive technique and the sensitivity and specificity of this technique not high enough for early detection that leads to unacceptability. In contrast, sputu
Data Loading...
